A method for intelligent sensing and adaptive estimation of bearing behavior of pressure-type anchor rods

Abstract

The application discloses a pressure type anchor rod bearing property intelligent sensing and self-adaptive estimation method and relates to the technical field of geotechnical engineering, and comprises the following steps: acquiring key nodes of a pressure type anchor rod and acquiring bearing property influence data of the pressure type anchor rod; a bearing property influence coefficient model is constructed based on a machine learning algorithm according to the bearing property influence data; parameters in the bearing property influence model are estimated based on linear regression analysis, and self-adaptive estimation is performed by inputting the estimated parameters; and the bearing property influence model is constructed, so that the problems of reducing construction risks, improving engineering quality and safety are solved.

Description

Technical Field

[0001] This invention relates to the field of geotechnical engineering technology, and more specifically, to a method for intelligent sensing and adaptive prediction of the bearing characteristics of pressure-type anchor bolts. Background Technology

[0002] In modern civil engineering, particularly in slope protection and underground engineering, anchor bolts are crucial support components, and the stability and reliability of their load-bearing performance are paramount. Pressure anchor bolts, with their unique support properties, transfer pressure from the slope rock mass to stable rock or soil layers through a pressure system formed by the anchor bolt and grout, providing stable support force for the slope. However, the load-bearing characteristics of anchor bolts are comprehensively influenced by geological conditions, engineering factors, and the inherent properties of the anchor bolts themselves, making the prediction and analysis of anchor bolt load-bearing capacity a complex and critical issue.

[0003] The above-disclosed technical solutions have at least the following technical problems:

[0004] However, traditional monitoring methods often rely on manual inspections and periodic testing, resulting in problems such as low monitoring frequency, discontinuous data, and inability to monitor in real time. Furthermore, due to the complexity and uncertainty of geotechnical engineering, traditional empirical formulas and calculation methods often struggle to accurately predict the bearing capacity of anchor bolts. To address these issues, this invention proposes a solution. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide an intelligent perception and adaptive prediction method for the bearing characteristics of pressure-type anchor bolts. By constructing a bearing characteristics influence model, this method aims to address issues related to reducing construction risks and improving project quality and safety.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A method for intelligent sensing and adaptive prediction of the bearing characteristics of a pressure anchor bolt includes: acquiring key nodes of the pressure anchor bolt and acquiring bearing characteristic influence data of the pressure anchor bolt; constructing a bearing characteristic influence coefficient model based on the bearing characteristic influence data using a machine learning algorithm; predicting the parameters in the bearing characteristic influence model based on linear regression analysis; and performing adaptive prediction by inputting the predicted parameters.

[0008] In a preferred embodiment, the bearing capacity influence data includes an anchoring force influence coefficient. The steps for obtaining the anchoring force influence coefficient are as follows: Obtain the diameter of the anchor rod and the depth of the anchor rod embedded in the soil medium; collect the pressure data borne by the anchor rod, preprocess the pressure data to remove outliers, and average the preprocessed pressure data to obtain the average pressure borne by the anchor rod; select multiple groups of anchor rods of the same material, perform limit tests on each group of anchor rods to obtain the maximum bearing pressure of each group of anchor rods, average the maximum bearing pressure data of multiple groups of anchor rods to obtain the average maximum bearing pressure, and use the average maximum bearing pressure as a standard value; select a group of anchor rods to be tested, apply pressure to the anchor rod, and continuously increase the pressure, recording the frictional force experienced by the anchor rod under different pressures. The relationship between pressure and friction is analyzed linearly to obtain the material property index and the friction coefficient of the anchoring surface. The soil and rock types, density, and water content of the area where the anchor is used are obtained. The friction stress of the soil and rock medium and the shear strength of the rock are obtained through direct shear tests. The lowest and highest temperatures of the area under test in previous years are obtained to form a temperature range. Within this temperature range, the expansion change data of the anchor material are recorded. The relationship between temperature and expansion change is analyzed using linear analysis to obtain the temperature influence coefficient. Based on the diameter of the anchor, the depth of the anchor embedded in the soil and rock medium, the pressure borne by the anchor, the maximum bearing pressure, the material property index, the friction coefficient of the anchoring surface, the friction stress of the soil and rock medium, the shear strength of the rock, and the temperature influence coefficient, the anchoring force influence coefficient is calculated using a preset formula, resulting in the anchoring force influence coefficient.

[0009] In a preferred embodiment, the bearing capacity influence data includes the soil and rock medium property influence coefficient. The steps for obtaining the soil and rock medium property influence coefficient are as follows: A triaxial shear test is performed on the area to be tested, and the shear strength of the soil under different stress conditions is recorded. The obtained shear strength data is fitted to obtain the internal friction angle of the soil and rock medium and the current friction angle of the soil and rock medium; the soil of the area to be tested is obtained, and a shaking table density test is performed on the soil to obtain the density of the soil and rock medium; a new soil sample of the area to be tested is obtained, and a dry density test is performed in the laboratory to obtain the standard density of the soil; the soil of the area to be tested is obtained, and a triaxial undrained shear test is performed, applying different stresses to the soil and recording the cohesion values ​​of the soil under different stresses. The cohesion of the soil under the maximum stress condition is obtained from the soil cohesion value data; different densities and friction angles are obtained. Test data on the bearing capacity of anchor bolts under friction angle conditions were collected and preprocessed. Regression analysis was then performed on the preprocessed data to obtain the influence coefficients of density and friction angle. Multiple groups of soils with different cohesion were collected, and the bearing capacity of these soils was tested to obtain the bearing capacity of the soils under different cohesion. The influence coefficients of the nonlinear relationship between soil cohesion and soil bearing capacity were obtained based on the fitting method. The influence coefficients of soil properties were calculated based on the internal friction angle of the soil and rock medium, the current friction angle of the soil and rock medium, the density of the soil and rock medium, the standard density of the soil, the cohesion of the soil under maximum stress conditions, the influence coefficients of density, friction angle, nonlinear relationship of soil cohesion, and nonlinear relationship of soil bearing capacity, according to a preset formula for the influence coefficients of soil and rock medium properties.

[0010] In a preferred embodiment, the bearing capacity influence data includes an external load influence coefficient. The steps for obtaining the external load influence coefficient are as follows: acquiring characteristic parameters of the external load, including seismic load, wind load, and mechanical load; calculating the maximum bearing capacity of the anchor rod under no external load, i.e., the critical load, through static analysis; acquiring historical load response data of the anchor rod, filtering the historical load response data to remove outliers, and analyzing the processed data to obtain the load application time; selecting multiple groups of anchor rods of the same material to be tested, applying external loads to the anchor rods until damage occurs, and recording the time the anchor rods endure under the external load; summing the application times of multiple groups of anchor rods and averaging them as the maximum application time of the external load; experimentally measuring the bearing capacity of the anchor rods under different load application times to obtain the relationship data between load time and bearing capacity; performing regression analysis on the relationship data between load time and bearing capacity to obtain the influence index of load time on bearing capacity; and then... The frequency spectrum of the load signal is obtained through spectral analysis, thus revealing the time interval of load changes, which is the external load period. The behavior of anchor bolts under different periodic loads is simulated to obtain the bearing capacity of the anchor bolts under different periods. The influence index of the period on the bearing capacity is obtained based on regression analysis. A group of anchor bolts to be tested is selected, and different levels of external loads are applied to them. The change data of the anchor bolt bearing capacity under different external loads are recorded, and the coefficient of the external load intensity is obtained based on linear analysis. Through the data relationship between load application time, period, and bearing capacity, regression analysis is performed to obtain the coefficients of the external load application time and the external load period. Based on the critical load, external load, load application time, maximum external load application time, the influence index of load time on bearing capacity, external load period, the influence index of period on bearing capacity, the coefficient of external load intensity, the coefficient of external load application time, and the coefficient of external load period, the external load influence coefficient is calculated using a preset external load influence coefficient formula to obtain the external load influence coefficient.

[0011] In a preferred embodiment, the parameters in the bearing capacity influence model are estimated based on linear regression analysis, and adaptive estimation is performed by inputting the estimated parameters. Specifically, key feature parameters are extracted from the bearing capacity influence data, including anchor diameter, anchor depth embedded in the soil and rock medium, maximum anchor bearing pressure, rock shear strength, soil friction angle, soil cohesion, and external load. The key feature parameters are estimated, and the estimated parameters are input into the bearing capacity influence coefficient model to obtain the estimated bearing capacity influence coefficient. If the estimated bearing capacity influence coefficient is lower than a preset value, construction is stopped.

[0012] The technical effects and advantages of the intelligent sensing and adaptive prediction method for the bearing characteristics of pressure-type anchor bolts of this invention are as follows:

[0013] 1. The intelligent sensing and prediction system for the bearing characteristics of pressure-type anchor bolts of the present invention includes an intelligent sensing unit, a data acquisition and processing module, an adaptive prediction model, and a user interface. The data acquisition and processing module integrates high-precision sensors and intelligent data processing algorithms to achieve accurate monitoring of the stress state and deformation characteristics of the anchor bolts, thereby improving the accuracy and reliability of the data.

[0014] 2. The intelligent sensing and prediction system for the bearing characteristics of pressure-type anchor bolts of the present invention includes an intelligent sensing unit, a data acquisition and processing module, an adaptive prediction model, and a user interface. The intelligent sensing unit monitors the bearing characteristics of the anchor bolts in real time, promptly detects potential safety hazards, and reduces risks during construction.

[0015] 3. The intelligent sensing and prediction system for the bearing characteristics of pressure-type anchor bolts of the present invention includes an intelligent sensing unit, a data acquisition and processing module, an adaptive prediction model, and a user interface. Based on the prediction results of the adaptive prediction model, the design parameters of the anchor bolts are optimized and adjusted to improve the scientificity and rationality of engineering design. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the structure of a method for intelligent sensing and adaptive prediction of the bearing characteristics of a pressure-type anchor bolt according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0018] In modern civil engineering, particularly in slope protection and underground engineering, anchor bolts are crucial support components, and the stability and reliability of their load-bearing performance are paramount. Pressure anchor bolts, with their unique support properties, transfer pressure from the slope rock mass to stable rock or soil layers through a pressure system formed by the anchor bolt and grout, providing stable support force for the slope. However, the load-bearing characteristics of anchor bolts are comprehensively influenced by geological conditions, engineering factors, and the inherent properties of the anchor bolts themselves, making the prediction and analysis of anchor bolt load-bearing capacity a complex and critical issue.

[0019] Traditional monitoring methods often rely on manual inspections and periodic testing, which suffer from problems such as low monitoring frequency, discontinuous data, and inability to monitor in real time. Furthermore, due to the complexity and uncertainty of geotechnical engineering, traditional empirical formulas and calculation methods often fail to accurately predict the bearing capacity of anchor bolts.

[0020] Example 1, Figure 1 This invention presents an intelligent sensing and adaptive prediction method for the bearing characteristics of pressure-type anchor bolts, comprising the following steps:

[0021] S1, obtain the sensor node of the pressure anchor bolt, and collect data on the influence of bearing characteristics through the sensor.

[0022] In this embodiment, the sensor node for acquiring the pressure-type anchor bolt collects data on the influence of bearing characteristics through sensors, as detailed below:

[0023] The data on the influence of bearing characteristics include the anchoring force influence coefficient, the soil and rock medium property influence coefficient, and the external load influence coefficient, as detailed below:

[0024] The anchoring force influence coefficient is a complex coefficient that comprehensively considers the interaction between the anchor and the soil / rock medium, the anchoring depth, the anchoring method, and various physical parameters. It is calculated using a specific formula, involving factors such as anchor diameter, anchoring length, anchor stress, maximum bearing pressure, soil / rock friction stress, and rock shear strength. Furthermore, it considers material correlation coefficients, friction coefficients and material property indices, as well as coefficients describing the relationship between anchoring depth and bearing characteristics, and the influence of temperature. This coefficient is of great significance for evaluating the anchoring effect of anchors.

[0025] The specific steps for obtaining the anchoring force influence coefficient are as follows:

[0026] Obtain the diameter of the anchor bolt and the depth at which the anchor bolt is embedded in the soil or rock medium;

[0027] Collect the pressure data of the anchor bolts, preprocess the pressure data of the anchor bolts to remove outliers, and add up the preprocessed pressure data of the anchor bolts and average them to obtain the average pressure of the anchor bolts.

[0028] Select multiple groups of anchor bolts made of the same material, conduct limit tests on each group of anchor bolts to obtain the maximum bearing pressure of each group of anchor bolts, average the maximum bearing pressure data of multiple groups of anchor bolts to obtain the average maximum bearing pressure, and use the average maximum bearing pressure as the standard value.

[0029] Select a set of anchor rods to be tested, apply pressure to the anchor rods and continuously increase the pressure, and record the friction force on the anchor rods under different pressures. By linearly analyzing the relationship between pressure and friction force, the material property index and the friction coefficient of the anchoring surface are obtained.

[0030] The soil and rock types, density, and water content of the area where the anchor bolts are used are obtained, and the frictional stress of the soil and rock media and the shear strength of the rock are obtained through direct shear tests.

[0031] The lowest and highest temperatures of the area to be tested in previous years are obtained to form a temperature range. Within this temperature range, the expansion change data of the anchor material are recorded. The relationship between temperature and expansion change is analyzed based on the linear analysis method to obtain the temperature influence coefficient.

[0032] The anchoring force influence coefficient is calculated based on the anchor diameter, the depth of the anchor buried in the soil and rock medium, the pressure borne by the anchor, the maximum bearing pressure, the material property index, the friction coefficient of the anchoring surface, the friction stress of the soil and rock medium, the shear strength of the rock, and the temperature influence coefficient, according to the preset anchoring force influence coefficient formula.

[0033] The specific formula for calculating the anchoring force influence coefficient is as follows:

[0034]

[0035] In the formula, It is the anchoring force influence coefficient. It is the diameter of the anchor bolt. It is the depth to which the anchor bolt is embedded in the soil or rock medium. It is the coefficient of friction of the anchoring surface. It is a material property index. It is the pressure borne by the anchor bolt. It is the maximum bearing pressure. It is an adjustment factor. It is the material correlation coefficient. It is the deep correlation coefficient. It is the temperature influence coefficient. It is the frictional stress of the soil and rock medium. It is the shear strength of the rock.

[0036] The soil and rock properties influence coefficient is a parameter that comprehensively considers the impact of factors such as soil and rock hardness, friction coefficient, and density on the bearing capacity of anchor bolts. This coefficient is calculated through a complex mathematical formula, involving the difference between the internal friction angle and the standard internal friction angle of the soil and rock, the ratio of soil and rock density to standard density, and the ratio of soil cohesion to maximum cohesion.

[0037] The specific steps for obtaining the influence coefficient of the soil and rock medium properties are as follows:

[0038] Triaxial shear tests were conducted on the area to be tested, and the shear strength of the soil under different stress conditions was recorded. The obtained shear strength data were fitted to obtain the internal friction angle of the soil and rock medium and the friction angle of the current soil and rock medium.

[0039] The soil from the area to be tested is obtained, and the density of the soil is obtained by a shaking table test.

[0040] Obtain a new soil sample from the area to be tested, and conduct a dry density test in the laboratory to obtain the standard density of the soil.

[0041] The soil in the test area was obtained based on a triaxial undrained shear test. Different stresses were applied to the soil, and the cohesion values ​​of the soil under different stresses were recorded. The cohesion of the soil under the maximum stress condition was obtained from the soil cohesion data.

[0042] Test data on the bearing capacity of anchor bolts under different densities and friction angles were obtained, and the test data were preprocessed. Regression analysis was performed on the preprocessed data to obtain the influence coefficients of density and friction angle.

[0043] Multiple groups of soils with different cohesion were collected, and the bearing capacity of the soils was tested to obtain the bearing capacity of the soils under different cohesion. Based on the fitting method, the influence coefficients of the nonlinear relationship of soil cohesion and the nonlinear relationship of soil bearing capacity were obtained.

[0044] The influence coefficient of soil and rock characteristics is calculated based on the internal friction angle of the soil and rock medium, the current friction angle of the soil and rock medium, the density of the soil and rock medium, the standard density of the soil, the cohesion of the soil under maximum stress conditions, the influence coefficient of density, the influence coefficient of friction angle, the influence coefficient of the nonlinear relationship of soil cohesion, and the influence coefficient of the nonlinear relationship of soil bearing capacity, according to the preset formula for the influence coefficient of soil and rock characteristics.

[0045] The specific formula for calculating the influence coefficient of soil and rock media properties is as follows:

[0046]

[0047] In the formula, It is the influence coefficient of soil and rock medium properties. It is the internal friction angle of the soil and rock medium. It is the friction angle of the current soil and rock medium. It is the coefficient of influence of the friction angle. It is the influence coefficient of density. It is the density of the soil and rock medium. It is the standard density. It is an index of the influence of density on bearing capacity. It is the influence coefficient of the nonlinear relationship of soil cohesion. It is the influence coefficient of the nonlinear relationship of soil bearing capacity. It is the cohesive force of the soil. It is the cohesion of soil under maximum stress conditions.

[0048] The external load influence coefficient is a parameter that measures the degree of influence of external loads (such as earthquakes, wind, or mechanical loads) on the anchor bolt's bearing capacity. Its calculation formula integrates the effects of the external load's intensity, duration, and period on the anchor bolt's performance. Specifically, the intensity of the external load is reflected by the ratio of the load to the critical load, and its influence is controlled by coefficients and exponents; the load's duration is described by the time-influence exponent, while the influence of the load period is characterized by the period coefficient. The combined effect of the external load influence coefficient reveals the dynamic changes in the anchor bolt's bearing capacity caused by load intensity, duration, and period. This coefficient is crucial in designing and evaluating the safety of anchor bolts, especially when considering complex environmental factors (such as earthquakes and storms).

[0049] The steps for obtaining the external load influence coefficient are as follows:

[0050] Obtain the characteristic parameters of the external loads, including seismic loads, wind loads, and mechanical loads;

[0051] The maximum bearing capacity of the anchor rod under no external load, i.e., the critical load, is calculated by static analysis.

[0052] Obtain historical load response data of anchor bolts, filter the historical load response data to remove outliers, and analyze the processed data to obtain the load application time.

[0053] Select multiple sets of anchor rods made of the same material to be tested, apply external loads to the anchor rods until they are damaged, and record the time the anchor rods bear the external load. Add up the time of multiple sets of anchor rods and average it as the maximum time of external load.

[0054] Experimental measurements of anchor bolt bearing capacity under different load application times were conducted to obtain data on the relationship between load time and bearing capacity. Regression analysis was performed on the data on the relationship between load time and bearing capacity to obtain the influence index of load time on bearing capacity.

[0055] The frequency spectrum of the load is obtained by spectral analysis of the load signal, and the time interval of load change is obtained. This time interval of load change is the external load period.

[0056] The behavior of anchor bolts under different periodic loads was simulated to obtain the bearing capacity of anchor bolts under different periods. The influence index of period on bearing capacity was obtained based on regression analysis.

[0057] Select a group of anchor rods to be tested, apply different levels of external loads to the anchor rods, and record the changes in the bearing capacity of the anchor rods under different external loads. Based on linear analysis, obtain the coefficient of external load strength.

[0058] By using the data relationship between load application time, period and bearing capacity, regression analysis is performed to obtain the coefficients of external load application time and external load period.

[0059] The external load influence coefficient is calculated based on the critical load, external load, load duration, maximum duration of external load, influence index of load duration on bearing capacity, external load period, influence index of period on bearing capacity, coefficient of external load intensity, coefficient of external load duration, and coefficient of external load period, using a preset formula for the external load influence coefficient.

[0060] The formula for calculating the external load influence coefficient is as follows:

[0061]

[0062] In the formula, It is the external load influence coefficient. It is an external load. It is the critical load. It is the duration of load application. It is the maximum duration of the external load. It is an index of the influence of load time on bearing capacity. It is a coefficient of the external load period. It is a coefficient of external load strength. It is a coefficient representing the duration of the external load. It is the period of the external load. It is a reference period. It is an index of the impact of the cycle on the bearing capacity.

[0063] S2, construct a bearing capacity influence coefficient model based on the bearing capacity influence data using a machine learning algorithm.

[0064] In this embodiment, the step of constructing a bearing capacity influence coefficient model based on the bearing capacity influence data using a machine learning algorithm is as follows:

[0065] The specific calculation formula for the bearing capacity influence coefficient model is as follows:

[0066]

[0067] In the formula, It is the bearing capacity influence coefficient. It is the anchoring force influence coefficient. It is the influence coefficient of soil and rock medium properties. It is the external load influence coefficient.

[0068] It should be noted that the bearing capacity influence coefficient reflects the overall strength and stability of the bearing capacity of the pressure anchor. A higher bearing capacity influence coefficient means that the anchor's bearing capacity is positively influenced by factors such as anchoring force, soil properties, external loads, and environmental factors, resulting in a stronger bearing capacity. Conversely, a lower bearing capacity influence coefficient may indicate that certain factors (such as poor soil conditions, excessive external loads, or harsh environments) negatively impact the anchor's bearing capacity, potentially leading to poor anchor performance or failure.

[0069] S3, based on linear regression analysis, predicts the parameters in the load-bearing property influence model, and performs adaptive prediction by inputting the predicted parameters.

[0070] In this embodiment, the parameters in the load-bearing characteristic influence model are estimated based on linear regression analysis, and adaptive estimation is performed by inputting the estimated parameters, as detailed below:

[0071] Key characteristic parameters are extracted from the bearing behavior influence data. These key characteristic parameters include anchor diameter, anchor depth embedded in the soil and rock medium, maximum anchor bearing pressure, rock shear strength, soil friction angle, soil cohesion, and external load.

[0072] Key characteristic parameters are estimated, and the estimated parameters are input into the bearing capacity influence coefficient model to obtain the estimated bearing capacity influence coefficient.

[0073] If the estimated load-bearing characteristic influence coefficient is lower than the preset value, construction shall be stopped.

[0074] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0075] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0076] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0077] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0078] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0079] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent sensing and adaptive prediction of the bearing characteristics of a pressure-type anchor bolt, characterized in that, Includes the following steps: Key nodes of pressure anchor bolts are obtained, and data on the bearing characteristics of pressure anchor bolts are obtained. The data on the bearing characteristics include the anchoring force influence coefficient, the soil and rock medium property influence coefficient, and the external load influence coefficient. Based on the data on the impact of bearing characteristics, a model of the bearing characteristics impact coefficient is constructed using a machine learning algorithm; The parameters in the load-bearing behavior influence model are estimated based on linear regression analysis, and adaptive estimation is performed by inputting the estimated parameters; The specific formula for calculating the anchoring force influence coefficient is as follows: In the formula, It is the anchoring force influence coefficient. It is the diameter of the anchor bolt. It is the depth to which the anchor bolt is embedded in the soil or rock medium. It is the coefficient of friction of the anchoring surface. It is a material property index. It is the pressure borne by the anchor bolt. It is the maximum bearing pressure. It is an adjustment factor. It is the material correlation coefficient. It is the deep correlation coefficient. It is the temperature influence coefficient. It is the frictional stress of the soil and rock medium. It is the shear strength of the rock; The specific formula for calculating the influence coefficient of soil and rock media properties is as follows: In the formula, It is the influence coefficient of soil and rock medium properties. It is the internal friction angle of the soil and rock medium. It is the friction angle of the current soil and rock medium. It is the coefficient of influence of the friction angle. It is the influence coefficient of density. It is the density of the soil and rock medium. It is the standard density. It is an index of the influence of density on bearing capacity. It is the influence coefficient of the nonlinear relationship of soil cohesion. It is the influence coefficient of the nonlinear relationship of soil bearing capacity. It is the cohesive force of the soil. It is the cohesion of the soil under maximum stress conditions; The formula for calculating the external load influence coefficient is as follows: In the formula, It is the external load influence coefficient. It is an external load. It is the critical load. It is the duration of load application. It is the maximum duration of the external load. It is an index of the influence of load time on bearing capacity. It is a coefficient of the external load period. It is a coefficient of external load strength. It is a coefficient representing the duration of the external load. It is the period of the external load. It is a reference period. It is an index of the impact of the cycle on the bearing capacity.

2. The intelligent sensing and adaptive prediction method for the bearing characteristics of a pressure-type anchor bolt according to claim 1, characterized in that, The data on the influence of bearing characteristics includes the anchoring force influence coefficient, and the specific steps for obtaining the anchoring force influence coefficient are as follows: Obtain the diameter of the anchor bolt and the depth at which the anchor bolt is embedded in the soil or rock medium; Collect the pressure data of the anchor bolts, preprocess the pressure data of the anchor bolts to remove outliers, and add up the preprocessed pressure data of the anchor bolts and average them to obtain the average pressure of the anchor bolts. Select multiple groups of anchor bolts made of the same material, conduct limit tests on each group of anchor bolts to obtain the maximum bearing pressure of each group of anchor bolts, average the maximum bearing pressure data of multiple groups of anchor bolts to obtain the average maximum bearing pressure, and use the average maximum bearing pressure as the standard value. Select a set of anchor rods to be tested, apply pressure to the anchor rods and continuously increase the pressure, and record the friction force on the anchor rods under different pressures. By linearly analyzing the relationship between pressure and friction force, the material property index and the friction coefficient of the anchoring surface are obtained. The soil and rock types, density, and water content of the area where the anchor bolts are used are obtained, and the frictional stress of the soil and rock media and the shear strength of the rock are obtained through direct shear tests. The lowest and highest temperatures of the area to be tested in previous years are obtained to form a temperature range. Within this temperature range, the expansion change data of the anchor material are recorded. The relationship between temperature and expansion change is analyzed based on the linear analysis method to obtain the temperature influence coefficient. The anchoring force influence coefficient is calculated based on the anchor diameter, the depth of the anchor buried in the soil and rock medium, the pressure borne by the anchor, the maximum bearing pressure, the material property index, the friction coefficient of the anchoring surface, the friction stress of the soil and rock medium, the shear strength of the rock, and the temperature influence coefficient, according to the preset anchoring force influence coefficient formula.

3. The intelligent sensing and adaptive prediction method for the bearing characteristics of a pressure-type anchor bolt according to claim 2, characterized in that, The bearing capacity influence data includes the soil and rock medium property influence coefficient, and the specific steps for obtaining the soil and rock medium property influence coefficient are as follows: Triaxial shear tests were conducted on the area to be tested, and the shear strength of the soil under different stress conditions was recorded. The obtained shear strength data were fitted to obtain the internal friction angle of the soil and rock medium and the friction angle of the current soil and rock medium. The soil from the area to be tested is obtained, and the density of the soil is obtained by a shaking table test. Obtain a new soil sample from the area to be tested, and conduct a dry density test in the laboratory to obtain the standard density of the soil. The soil in the test area was obtained based on a triaxial undrained shear test. Different stresses were applied to the soil, and the cohesion values ​​of the soil under different stresses were recorded. The cohesion of the soil under the maximum stress condition was obtained from the soil cohesion data. Test data on the bearing capacity of anchor bolts under different densities and friction angles were obtained, and the test data were preprocessed. Regression analysis was performed on the preprocessed data to obtain the influence coefficients of density and friction angle. Multiple groups of soils with different cohesion were collected, and the bearing capacity of the soils was tested to obtain the bearing capacity of the soils under different cohesion. Based on the fitting method, the influence coefficients of the nonlinear relationship of soil cohesion and the nonlinear relationship of soil bearing capacity were obtained. The influence coefficient of soil and rock characteristics is calculated based on the internal friction angle of the soil and rock medium, the current friction angle of the soil and rock medium, the density of the soil and rock medium, the standard density of the soil, the cohesion of the soil under maximum stress conditions, the influence coefficient of density, the influence coefficient of friction angle, the influence coefficient of the nonlinear relationship of soil cohesion, and the influence coefficient of the nonlinear relationship of soil bearing capacity, according to the preset formula for the influence coefficient of soil and rock characteristics.

4. The intelligent sensing and adaptive prediction method for the bearing characteristics of a pressure-type anchor bolt according to claim 3, characterized in that, The load-bearing behavior influence data includes the external load influence coefficient, and the specific steps for obtaining the external load influence coefficient are as follows: Obtain the characteristic parameters of the external loads, including seismic loads, wind loads, and mechanical loads; The maximum bearing capacity of the anchor rod under no external load, i.e., the critical load, is calculated by static analysis. Obtain historical load response data of anchor bolts, filter the historical load response data to remove outliers, and analyze the processed data to obtain the load application time. Select multiple sets of anchor rods made of the same material to be tested, apply external loads to the anchor rods until they are damaged, and record the time the anchor rods bear the external load. Add up the time of multiple sets of anchor rods and average it as the maximum time of external load. Experimental measurements of anchor bolt bearing capacity under different load application times were conducted to obtain data on the relationship between load time and bearing capacity. Regression analysis was performed on the data on the relationship between load time and bearing capacity to obtain the influence index of load time on bearing capacity. The frequency spectrum of the load is obtained by spectral analysis of the load signal, and the time interval of load change is obtained. This time interval of load change is the external load period. The behavior of anchor bolts under different periodic loads was simulated to obtain the bearing capacity of anchor bolts under different periods. The influence index of period on bearing capacity was obtained based on regression analysis. Select a group of anchor rods to be tested, apply different levels of external loads to the anchor rods, and record the changes in the bearing capacity of the anchor rods under different external loads. Based on linear analysis, obtain the coefficient of external load strength. By using the data relationship between load application time, period and bearing capacity, regression analysis is performed to obtain the coefficients of external load application time and external load period. The external load influence coefficient is calculated based on the critical load, external load, load duration, maximum duration of external load, influence index of load duration on bearing capacity, external load period, influence index of period on bearing capacity, coefficient of external load intensity, coefficient of external load duration, and coefficient of external load period, using a preset formula for the external load influence coefficient.

5. The intelligent sensing and adaptive prediction method for the bearing characteristics of a pressure-type anchor bolt according to claim 4, characterized in that, The parameters in the load-bearing behavior influence model are estimated based on linear regression analysis, and adaptive estimation is performed by inputting the estimated parameters, as detailed below: Key characteristic parameters are extracted from the bearing behavior influence data. These key characteristic parameters include anchor diameter, anchor depth embedded in the soil and rock medium, maximum anchor bearing pressure, rock shear strength, soil friction angle, soil cohesion, and external load. Key characteristic parameters are estimated, and the estimated parameters are input into the bearing capacity influence coefficient model to obtain the estimated bearing capacity influence coefficient. If the estimated load-bearing characteristic influence coefficient is lower than the preset value, construction shall be stopped.

6. The intelligent sensing and adaptive prediction method for the bearing characteristics of a pressure-type anchor bolt according to claim 5, characterized in that, The specific calculation formula for the bearing capacity influence coefficient model is as follows: In the formula, It is the bearing capacity influence coefficient. It is the anchoring force influence coefficient. It is the influence coefficient of soil and rock medium properties. It is the external load influence coefficient.

Images